Patents by Inventor David Buchanan
David Buchanan has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11847575Abstract: A dynamic reasoning system may include a symbolic reasoning engine that iteratively calls a dynamic rule generator to answer an input query. The symbolic reasoning engine may determine a primary goal and/or secondary goals to generate proofs for the answer. The symbolic reasoning engine may call a rules component to provide rules to prove a current input goal. The rules component may use a static rule knowledge base and/or the dynamic rule generator to retrieve and rank rules relevant to the current input goal. The dynamic rule generator may generate new rules that lead to the current input goal. The dynamic rule generator may include a statistical model that generates unstructured or structured probabilistic rules based on context related to the input query. The symbolic reasoning engine may return a list of rules with confidence for explaining the answer to the input goal.Type: GrantFiled: September 1, 2020Date of Patent: December 19, 2023Assignee: Elemental Cognition Inc.Inventors: David Ferrucci, Aditya Kalyanpur, Jennifer Chu-Carroll, Thomas Breloff, Or Biran, David Buchanan
-
Publication number: 20220067540Abstract: A dynamic reasoning system may include a symbolic reasoning engine that iteratively calls a dynamic rule generator to answer an input query. The symbolic reasoning engine may determine a primary goal and/or secondary goals to generate proofs for the answer. The symbolic reasoning engine may call a rules component to provide rules to prove a current input goal. The rules component may use a static rule knowledge base and/or the dynamic rule generator to retrieve and rank rules relevant to the current input goal. The dynamic rule generator may generate new rules that lead to the current input goal. The dynamic rule generator may include a statistical model that generates unstructured or structured probabilistic rules based on context related to the input query. The symbolic reasoning engine may return a list of rules with confidence for explaining the answer to the input goal.Type: ApplicationFiled: September 1, 2020Publication date: March 3, 2022Applicant: Elemental OpCo, LLCInventors: David Ferrucci, Aditya Kalyanpur, Jennifer Chu-Carroll, Thomas Breloff, Or Biran, David Buchanan
-
Patent number: 10657205Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: GrantFiled: March 20, 2017Date of Patent: May 19, 2020Assignee: ELEMENTAL COGNITION LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Patent number: 10650099Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: GrantFiled: March 20, 2017Date of Patent: May 12, 2020Assignee: ELMENTAL COGNITION LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Patent number: 10628523Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: GrantFiled: March 20, 2017Date of Patent: April 21, 2020Assignee: ELEMENTAL COGNITION LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Patent number: 10621285Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: GrantFiled: March 20, 2017Date of Patent: April 14, 2020Assignee: ELEMENTAL COGNITION LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Patent number: 10614166Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: GrantFiled: March 20, 2017Date of Patent: April 7, 2020Assignee: ELEMENTAL COGNITION LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Patent number: 10614165Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: GrantFiled: March 20, 2017Date of Patent: April 7, 2020Assignee: ELEMENTAL COGNITION LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Patent number: 10606952Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: GrantFiled: June 24, 2016Date of Patent: March 31, 2020Assignee: ELEMENTAL COGNITION LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Patent number: 10599778Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: GrantFiled: March 20, 2017Date of Patent: March 24, 2020Assignee: ELEMENTAL COGNITION LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Publication number: 20200034421Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: ApplicationFiled: March 20, 2017Publication date: January 30, 2020Applicant: Elemental Cognition LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu--Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Publication number: 20200034427Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: ApplicationFiled: March 20, 2017Publication date: January 30, 2020Applicant: Elemental Cognition LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu--Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Publication number: 20200034423Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: ApplicationFiled: March 20, 2017Publication date: January 30, 2020Applicant: Elemental Cognition LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu--Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Publication number: 20200034420Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: ApplicationFiled: March 20, 2017Publication date: January 30, 2020Applicant: Elemental Cognition LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Publication number: 20200034422Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: ApplicationFiled: March 20, 2017Publication date: January 30, 2020Applicant: Elemental Cognition LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu--Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Publication number: 20200034424Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: ApplicationFiled: March 20, 2017Publication date: January 30, 2020Applicant: Elemental Cognition LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu--Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Publication number: 20200034428Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: ApplicationFiled: March 20, 2017Publication date: January 30, 2020Applicant: Elemental Cognition LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu--Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Patent number: 10496754Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: GrantFiled: March 20, 2017Date of Patent: December 3, 2019Assignee: Elemental Cognition LLCInventors: David Ferrucci, Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang
-
Publication number: 20180100477Abstract: A fuel injector is provided that includes various precise configuration parameters, including dimensions, shape and/or relative positioning of fuel injector features, resulting in improved efficiency of fuel flow through the fuel injector.Type: ApplicationFiled: December 13, 2017Publication date: April 12, 2018Applicant: CUMMINS INTELLECTUAL PROPERTY, INC.Inventors: Lester PETERS, Jeffrey HUANG, David BUCHANAN, Corydon Edward MORRIS, Gary GANT, Denis GIL, Heribert KAMMERSTETTER, Ernst WINKLHOFER
-
Publication number: 20170371861Abstract: An architecture and processes enable computer learning and developing an understanding of arbitrary natural language text through collaboration with humans in the context of joint problem solving. The architecture ingests the text and then syntactically and semantically processes the text to infer an initial understanding of the text. The initial understanding is captured in a story model of semantic and frame structures. The story model is then tested through computer generated questions that are posed to humans through interactive dialog sessions. The knowledge gleaned from the humans is used to update the story model as well as the computing system's current world model of understanding. The process is repeated for multiple stories over time, enabling the computing system to grow in knowledge and thereby understand stories of increasingly higher reading comprehension levels.Type: ApplicationFiled: June 24, 2016Publication date: December 28, 2017Inventors: Mike Barborak, David Buchanan, Greg Burnham, Jennifer Chu-Carroll, David Ferrucci, Aditya Kalyanpur, Adam Lally, Stefano Pacifico, Chang Wang